Type | ID | Name | Comments |
Classification | 1 | Fisher | 线性判别分类器 |
Classification | 2 | Logistic 对数几率回归 | 1.IRLS(Newton-Raphson)Iteratively reweithted LS 迭代加权最小二乘; 2.Gradient Ascent梯度上升; 3.Stochastic Gradient Aescent (随机梯度下降,大规模数据,online); |
Classification | 3 | K-Nearest Neighbor(KNN) | K-最近邻分类器 |
Classification | 4 | Naïve Bayes | 朴素贝叶斯分类器 |
Classification | 5 | Soft Independent Modelling of Class Analogy(SIMCA) | 簇类独立软模式分类器 |
Classification | 6 | Perceptron 感知机(二元线性分类器) | 1.Standard(online); 2.Pocket(online); 3.Batch; |
Classification | 7 | Decision Tree-C4.5决策树 | Gain Ration增益率 |
Classification | 8 | Decision Tree-ID3决策树 | Information Entropy信息熵 |
Classification | 9 | Multinomial Logistic(Softmax) | 多类别逻辑回归 |
Classification | 10 | NN前馈神经⽹络/ MLP 多层感知机 | 1.Back Propagation(BP误差逆传播算法); 2.Stochastic Gradient Descent (随机梯度下降SGD),大规模数据; 3.Sequence; 4.Mini-Batch; 5.Batch; 6.Nesterov动能法Nesterov’s momentum method(SGD with Monentum); |
RC | 11 | CART分类与回归树 | 二叉树,连续变量,最小二乘回归树, 平方误差最小,离散变量: Gini Index基尼系数 |
RC | 12 | Partial Least Squares(PLS) | 偏最小二乘法(PLSR,PLSA) |
RC | 13 | Support Vector Machine(SVM) | 支持向量机(SVMR,SVMC) |
RC | 14 | Gaussian Process | 高斯过程 (GPR, GPC) |
Regression | 15 | Multiple Linear Regression(MLR) | 多元线性回归 |
Regression | 16 | Principal Component Regression(PCR) | 主成分回归 |
Regression, DR | 17 | Ridge Regression | 岭回归(L2约束) |
Regression, DR | 18 | Forward Stagewise linear regression(FSW) | 向前逐段回归,类似RR |
Regression, DR | 19 | Least Angle Regression(LARS) | 最小角回归 |
Regression, DR | 20 | LASSO套索(L1约束) | Lasso回归主要的解法: 1.ADMM交替方向乘子法Alternating Direction Method of Multipliers(拉格朗日方求解L1约束,大规模问题); 2.最小角回归法( Least Angle Regression)LARS; 3.坐标下降法(Coordinate Descent) ; 4.近点梯度法Proximal Gradient; 5.Nesterov动能法Nesterov’s momentum method; 6.优化-最小化算法Minorization-Maximization; |
Regression, DR | 21 | Elastic Net弹性网(L1+L2约束) | Coordinate Descent坐标下降法 |
Regression, DR | 22 | Kernel Ridge Regression | 核岭回归 |
Cluster | 23 | K-Means | K均值聚类 |
Cluster | 24 | FCMeans | 模糊C均值聚类 |
Cluster | 25 | GA-FCM | 基于遗传算法的模糊C均值聚类 |
Cluster | 26 | GA-K-Means | 基于遗传算法的K均值聚类 |
Cluster | 27 | PSO-K-Means | 基于粒子群算法的K均值聚类 |
Cluster | 28 | ACO-K-Means | 基于蚁群算法的K均值聚类 |
Cluster | 29 | TS-K-Means | 基于禁忌搜索算法的K均值聚类 |
Cluster | 30 | IA-K-Means | 基于免疫算法的K均值聚类 |
Cluster | 31 | Density-Based Spatial Clustering of Application with Noise(DBSCAN) | 密度聚类 |
Cluster | 32 | Jarvis-Patrick聚类 | 1. Breadth First Search广度优先遍历; 2. Depth First Search深度优先遍历; |
Cluster | 33 | Agglomerative NESting | AGNES 层次聚类 |
Cluster | 34 | Gaussian Mixture Model(GMM) (EC) | 混合高斯模型聚类 |
Cluster | 35 | Spectral Clustering | 谱聚类LE+KMeans |
Cluster | 36 | Self Organizing Maps(SOM) | 自组织映射神经网络,一种基于神经网络的聚类算法 |
Cluster | 37 | LVQ Cluster | 学习向量量化监督聚类 |
DR | 38 | Principal Component Analysis(PCA) | 主成分分析 1. SVD;2. NIPALS非线性迭代偏最小二乘算法Nonlinear iterative partial least squares algorithm; |
DR | 39 | Kernel PCA | 核主成分分析 |
DR | 40 | Feature Embedding | 特征嵌入p>>N |
DR | 41 | Independent Component Analysis(ICA) | 独立分量分析 |
DR | 42 | Nonnegative Matrix Factorization(NMF) 非负矩阵分解 | 1.Gradient Descent梯度下降; 2.ANLS,非负交替最小二乘法Alternating least square method; 3.NeNMF: An Optimal Gradient Method for Nonnegative Matrix Factorization; 4.CNMF; 5.Multiplicative Update; |
DR | 43 | Factor Analysis | 因子分析 |
DR | 44 | Multidimensional Scaling(MDS) | 多维尺度分析 |
DR | 45 | Isometrix Mapping(Isomap) | 等度量映射/等距特征映射 Shortest Path Algorithm最短路径 |
DR | 46 | Locally Linear Embedding(LLE) | 局部线性嵌入 |
DR | 47 | Locality Preserving Projection(LPP) | 局部保留投影法 |
DR | 48 | Laplacian Eigenmap(LE) | 拉普拉斯特征映射,相似性:1.KNN;2.Gaussian;3.LocalScaling;4.KNNGaussian;5.KNNLocalScalling |
DR | 49 | SVD | 特征值分解 |
MCA | 50 | Multivariate Curve Resolution-Alternating Least Squares(MCR-ALS) | 多元曲线分辨-交替最小二乘法(NNLS) |
MCA | 51 | Generalized Rank Annihilation Method(GRAM) | 广义秩消因子法 |
MCA | 52 | Direct Trilinear Decomposition(DTLD) | 直接三线性分解 |
MCA | 53 | CANDECOMP/PARAFAC | 典范/平行因子分析 |
MCA | 54 | Alternating Trilinear Decomposition(ATLD) | 交替三线性分解 |
MCA | 55 | SWATLD | 自加权交替三线性分解 |
MCA | 56 | APTLD | 交替惩罚三线性分解· |
MCA | 57 | Window Factor Analysis(WFA) | 窗口因子分解 |
MCA | 58 | Heuristic Evolving Latent Projection(HELP) | 启发渐进式特征投影 |
OPT | 59 | Genetic Algorithm(GA) | 遗传算法 |
OPT | 60 | Particle Swarm Optimization(PSO) | 粒子群优化算法 |
OPT | 61 | Differential Evolution Algorithm(DEA) | 差分进化算法 |
OPT | 62 | Ant Colony Optimization(ACO) | 蚁群算法 |
OPT | 63 | Immune Algorithm(IA) | 免疫算法 |
OPT | 64 | Simulate Anneal(SA) | 模拟退火算法 |
OPT | 65 | Tabu Search or Taboo Search(TS) | 禁忌搜索算法 |
Others | 66 | Kalman | 卡尔曼滤波,Mixture,估计-修正-估计-修正 |
Others | 67 | Curve Fitting 曲线拟合 | 1.Mixture Gaussian混合高斯;2.Polynomial多项式 |
Others | 68 | EA-Max/Min | 智能优化算法-最值问题 |
Others | 69 | EA-TSP | 智能优化算法-旅行商问题 |
Others | 70 | EA-Knapsack | 智能优化算法-背包问题 |
Others | 71 | Robust Principal Component Analysis(RPCA) | 稳健主成分分析 |
Base | 72 | Statics | 统计量 |
Base | 73 | Baseline Correction | 基线矫正(背景扣除) 1.ArPLS; 2.AirPLS; |
Base | 74 | Distance and Similarity 距离与相似性 | 1. Cosine余弦距离; 2. Minkowski 闵可夫斯基距离 Lp; 3. Euclidean欧氏距离L2; 4. Manhattan曼哈顿距离L1; 5. Chebyshev切比雪夫距离L; 6. Mahalanobis马氏距离; 7. Jaccard Coefficient杰卡德系数/Tanimoto; 8. Soergel塞格尔; 9. Bray Curtis/Czekanowski/Srenson Coefficient; 10. Hamming汉明距离; 11. Correlation 皮尔逊相关系数; 12. SNN相似度(Shared Nearest Neighbour); 13. Levenshtein 距离; 14. Damerau Levenshtein距离; |
Base | 75 | Smooth 平滑 | Moving Average,Median,Parzen,Exponential, Guassian,SavitzkyGolay,FFT,Wavelet |
Base | 76 | Peak | 峰值 |
Base | 77 | Normalize 归一化/标准化 | 1. Mean;2.Area;3.UnitVector; 4. Max;5. Range;6. Peak;7. MaxMin;8.ZSocre; |
Base | 78 | Histogram 直方图 | 非参数估计 |
Base | 79 | FFT/iFFT | 快速傅里叶变换 |
Base | 80 | Wavelet 小波变换 | 1.DWT; 2.CWT; 3.iDWT; |
Base | 81 | Compress(Wavelet) 压缩 | |
Base | 82 | Decompose(Wavelet) 分解 | 1.WithSampling:standard wavelet with sampling, 2.WithoutSampling:Low part is separated as even and odd two parts in this algorithm, |
Base | 83 | Expectation Maximization(EM) | 最大期望算法 |
Base | 84 | Convolution/Deconvolution | 卷积/去卷积 |
Base | 85 | AutoCorrelation/CrossCorrelation | 自相关/胡相关 |
Base | 86 | MSC | 多元散射校正 |
Base | 87 | Outlier | 离群值检测 |
Base | 88 | Feature Selection | 特征选择 |
CS | 89 | Orthogonal Matching Pursuit(OMP) | 正交匹配追踪 |
CS | 90 | Compressive sampling MP(CoSaMP) | 压缩采样匹配追踪 |
CS | 91 | Stagewise Matching Pursuit(StOMP) | 分段匹配追踪 |
CS | 92 | Weak Matching Pursuit(WMP) | 弱匹配追踪 |
CS | 93 | Subspace Pursuit(SP) | 子空间追踪 |
CS | 94 | Iterative Hard Threshold(IHT) | 迭代硬阈值算法 |
CS | 95 | Linearized Bregman | 线性Bregman |
Ensemble | 96 | Random Forest | 随机森林 |
Ensemble | 97 | Boosting | |
Ensemble | 98 | Bagging | |
BIO | 99 | Sequence Alignment | 基因序列比对 GlobalNeedlemanWunsch LocalSmithWaterman |
RC | 100 | NNT_MLP | 反馈神经网络(BP,LM,CG) |
Regression | 101 | NNT_RBF | KMeans-LS 径向基网络Radial Basis Networks |
Classification | 102 | NNT_Hamming | Compete NN, input 0/1 |
Classification | 103 | NNT_LVQ | Compete NN, cluster/classification, 学习向量量化Learning Vector Quantization |
Cluster | 104 | NNT_Kohonen | Compete NN, SOM, cluster |
107 | NNT_CNN | 卷积网络 |